Community source · Runtime untested. Licenses are included. Review scripts and hooks before installing; integrations may need your own keys or paid services. Browsing does not install or run tools.
Claude Code Templates ↗Use this agent to create, improve, and maintain project documentation. Specializes in technical writing, documentation standards, and generating documentation from code. Examples: Context: A user wants to add documentation to a new feature. user: 'Please help me document this new API endpoint.' assistant: 'I will use the documentation-expert to generate clear and concise documentation for your API.' The documentation-expert is the right choice for creating high-quality technical documentation. C
expert advisors1 file · MIT
Docusaurus documentation specialist. Use PROACTIVELY when working with Docusaurus documentation for site configuration, content management, theming, build troubleshooting, and deployment setup.
documentation1 file · MIT
Doom above the Claude Code prompt: a corridor shooter: imps, a shotgun, and the floor below. Plays while Claude works, pauses when the turn ends, keeps your best score; zero tokens. A single game split out of cc-arcade (MIT, Seza Akgün). Needs an interactive terminal with a mouse.
games9 files · MIT
Deterministic allergy tripwire for DoorDash CLI (dd-cli) checkouts. Before any 'dd-cli order checkout-url' (direct or via the dd-guard wrapper) it verifies that a fresh vetted-cart dump exists for that cart (written by the doordash-allergy-shield skill after vetting) and independently re-greps the dump against the anaphylaxis-severity allergens in the user's dietary profile plus their hidden-source synonyms (satay->peanut, aioli->egg, ponzu->soy/fish). Blocks with exit 2 when the dump is missing
doordash1 file · MIT
Append-only audit log of every DoorDash CLI (dd-cli) invocation made through Claude Code. A PostToolUse hook records one versioned JSON line per dd-cli command (timestamp, session, cwd, command with tokens stripped, event type derived from the command itself - search / cart_mutation / checkout_url / history - plus cart/order uuids when extractable) to ~/.claude/dd-guard/audit.jsonl. Answers 'what has my AI been ordering and what did it cost' with data instead of memory. Self-contained: captures
doordash1 file · MIT
View DoorDash spend vs caps, edit the dd-guard spending policy interactively, and reconcile the intent ledger against real order history
doordash1 file · MIT
Live allergen re-check for DoorDash CLI group orders. When a checkout runs for a cart that has a doordash-group-orders round ledger (.dd/round-*.json), this hook itself runs 'dd-cli cart show', joins cart lines to eaters via the person-to-cart-item-id ledger, and re-derives allergen conflicts against each eater's entry in the team-food.json roster - blocking with exit 2 on a live anaphylaxis-tier match. Verifies reality at checkout time instead of trusting a flag file: a skipped vetting step or
doordash1 file · MIT
Team lunch orchestration via DoorDash CLI - build a group round, emit checkout with split table, track payer rotation
doordash1 file · MIT
Manage saved DoorDash order playbooks (list, add from order history, remove, inspect) stored in ~/.claude/dd-cli/playbooks.json
doordash1 file · MIT
Manage the dietary profile (allergens with severity tiers, diets, dislikes) used by doordash-allergy-shield to vet DoorDash carts
doordash1 file · MIT
Spend and activity report for agent-driven DoorDash ordering - reconciles the audit log against real order history and renders totals, per-restaurant breakdown, repeat rate, and abandoned-cart rate
doordash1 file · MIT
Enforce the dd-guard spending gate for DoorDash CLI (dd-cli). Denies raw 'dd-cli order checkout-url' and 'dd-cli cart add-items' Bash calls that bypass the dd-guard.sh wrapper (installed by the doordash-spend-guard skill), and denies command-line writes to the policy file limits.json, which must only change through the interactive /doordash-budget command. Deterministic budget enforcement for agent-driven food ordering: a budget in a prompt is advisory, an exit-2 hook is not.
doordash1 file · MIT
Use when building .NET Core applications requiring cloud-native architecture, high-performance microservices, modern C# patterns, or cross-platform deployment with minimal APIs and advanced ASP.NET Core features. Specifically:\n\n \nContext: Building a microservices platform with multiple .NET 10 services that need cloud-native deployment, health checks, and distributed tracing across services.\nuser: "I need to build a system with 5 microservices in .NET 10 using minimal APIs, each with OpenAPI
programming languages1 file · MIT
Use this agent when working on legacy .NET Framework 4.8 enterprise applications that require maintenance, modernization, or integration with Windows-based infrastructure. Specifically:\n\n \nContext: User has a legacy ASP.NET Web Forms application running on .NET Framework 4.8 that needs security updates and performance optimization.\nuser: "We have a 10-year-old Web Forms application with ViewState bloat and some outdated security patterns. How can we modernize it without a complete rewrite?"\
programming languages1 file · MIT
Support development of .NET MAUI cross-platform apps with controls, XAML, handlers, and performance best practices.
data ai1 file · MIT
Perform janitorial tasks on C#/.NET code including cleanup, modernization, and tech debt remediation.
expert advisors1 file · MIT
Use this agent for installation guidance, usage examples, and automation patterns for the Droid CLI (Factory AI), with emphasis on droid exec for CI/CD and non-interactive automation. Examples: Context: A user wants to automate code review in their CI pipeline. user: 'How do I run Droid CLI in GitHub Actions to review every PR?' assistant: 'I will use the droid agent to show you a droid exec command and GitHub Actions integration for automated PR review.' The droid agent specializes in droid exe
expert advisors1 file · MIT
Expert assistant for Drupal development, architecture, and best practices using PHP 8.3+ and modern Drupal patterns
expert advisors1 file · MIT
Use this agent when optimizing the complete developer workflow including build times, feedback loops, testing efficiency, and developer satisfaction metrics across the entire development environment. Specifically:\n\n \nContext: A team reports slow development cycles with 3-minute build times, 2-minute test runs, and frustration with development server startup.\nuser: "Our developers are losing productivity due to slow builds and feedback loops. Build time is 3 minutes, tests take 2 minutes, and
development tools1 file · MIT
Manage and interact with the Dynatrace Platform for real-time observability and monitoring.
devtools1 file · MIT
The Dynatrace Expert Agent integrates observability and security capabilities directly into GitHub workflows, enabling development teams to investigate incidents, validate deployments, triage errors, detect performance regressions, validate releases, and manage security vulnerabilities by autonomously analysing traces, logs, and Dynatrace findings. This enables targeted and precise remediation of identified issues directly within the repository.
security1 file · MIT
Configure comprehensive end-to-end testing suite with framework selection and CI integration
testing1 file · MIT
Log all file edits to a project-local audit file with timestamps. Records every Edit tool usage to .claude/edit-log.txt for tracking changes across sessions. Requires jq.
development tools1 file · MIT
MCP server for connecting to Elasticsearch data and indices. Supports search queries, mappings, ES|QL, and shard information through natural language interactions.
devtools1 file · MIT
Our expert AI assistant for debugging code (O11y), optimizing vector search (RAG), and remediating security threats using live Elastic data.
security1 file · MIT
Code Review Mode tailored for Electron app with Node.js backend (main), Angular frontend (render), and native integration layer (e.g., AppleScript, shell, or native tooling). Services in other repos are not reviewed here.
web tools1 file · MIT
Use this agent when building Electron desktop applications that require native OS integration, cross-platform distribution, security hardening, and performance optimization. Use electron-pro for complete desktop app development from architecture to signed, distributable installers. Specifically:\n\n \nContext: A team is building a professional desktop productivity app for Windows, macOS, and Linux with auto-updates and system tray integration.\nuser: "We need to build a desktop note-taking app w
development team1 file · MIT
Official ElevenLabs MCP for text-to-speech, voice cloning, audio processing, and transcription. Generate AI voices, design custom voices, isolate audio, create sound effects, and more.
audio1 file · MIT
Use this agent when you need to build fault-tolerant, concurrent systems leveraging OTP patterns, GenServer architectures, and Phoenix framework for real-time applications. Specifically:\n\n \nContext: Building a real-time chat application with WebSocket support, process supervision, and multi-node clustering.\nuser: "I need to create a Phoenix LiveView chat app with custom GenServer state management, WebSocket channels, and the ability to cluster across multiple nodes. What's the best approach?
programming languages1 file · MIT
Use when developing firmware for resource-constrained microcontrollers, implementing RTOS-based applications, or optimizing real-time systems where hardware constraints, latency guarantees, and reliability are critical. Specifically:\n\n \nContext: A team is building firmware for an STM32F4-based IoT sensor that must operate on battery power for 6 months with strict latency requirements.\nuser: "We need firmware for a temperature/humidity sensor running on STM32F4 with 48KB RAM. Must wake every
programming languages1 file · MIT
